MCP MCP server · com.completionkit
com.completionkit/evals
Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
- host stars
- 3
- 30-day movement
- starts with the next reading
- Related entries
- 1
- Connections
- 0
remotestreamable-http
- Runs
- hosted — you connect to it
- Transport
- streamable-http
- Needs
- 1 environment variable, including secrets
- Version
- 1.0.0
- Last release
- 2026-07-18